Prediction of Sewer Pipe Deterioration Using Random Forest Classification

TL;DR

This paper develops a random forest classification model to predict sewer pipe deterioration, aiming to optimize inspection schedules and maintenance planning, with high accuracy demonstrated in a case study for Los Angeles.

Contribution

It introduces a novel application of random forest classification for sewer pipe condition prediction, improving inspection timing and maintenance decisions.

Findings

Achieved an ROC AUC of 0.81 indicating excellent predictive performance.

Reduced false negative and false positive rates in sewer pipe condition classification.

Demonstrated model effectiveness in a real-world case study for Los Angeles.

Abstract

Wastewater infrastructure systems deteriorate over time due to a combination of physical and chemical factors. Failure of this significant infrastructure could affect important social, environmental, and economic impacts. Furthermore, recognizing the optimized timeline for inspection of sewer pipelines are challenging tasks for the utility managers and other authorities. Regular examination of sewer networks is not cost-effective due to limited time and high cost of assessment technologies and a large inventory of pipes. To avoid such obstacles, various researchers endeavored to improve infrastructure condition assessment methodologies to maintain sewer pipe systems at the desired condition. Sewer condition prediction models are developed to provide a framework to forecast the future condition of pipes to schedule inspection frequencies. The main goal of this study is to develop a predictive model for wastewater pipes using random forest classification. Predictive models can effectively predict sewer pipe condition and can increase the certainty level of the predictive results and decrease uncertainty in the current condition of wastewater pipes. The developed random forest classification model has achieved a stratified test set false negative rate, the false positive rate, and an excellent area under the ROC curve of 0.81 in a case study application for the City of LA, California. An area under the ROC curve > 0.80 indicates the developed model is an "excellent" choice for predicting the condition of individual pipes in a sewer network. The deterioration models can be used in the industry to improve the inspection timeline and maintenance planning.